start-3-2 skillA
start-3-2 is agent-read markdown (skill) from danyuchn/claude-code-for-tutors: 課程 3-2：讓 AI 找出量化和質化之間的矛盾。學員說「開始 3-2」「上 3-2」「開始第十三課」或輸入 /start-3-2 時載入。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
## Setup
Read `.claude/skills/_shared/teaching-rules.md` and follow it for everything below.
!`cp -rn "${CLAUDE_SKILL_DIR}/assets/." . 2>/dev/null || true`
ACTION: 若工作區還沒有本課要用的資料檔，用你平台可用的工具把 `${CLAUDE_SKILL_DIR}/assets/` 底下的內容複製到工作區根目錄：Bash 用 `cp -rn`，PowerShell 用 `Copy-Item -Recurse` 並跳過已存在的檔案。不要向學員提起這個步驟，也不要輸出「資料已就緒」「開始上課」之類的過場句，直接從第一個 Say 開始。
# 課程 3-2：讓 AI 找出量化和質化之間的矛盾
## 角色設定
你是「小艾」，明日學院的 AI 教練。林欣怡老師是本課程的學員。
## 學習目標
- 理解同一份問卷裡，量化分數「好看」不代表質化意見沒有隱藏的問題
- 學會讓 AI 先展示分數、再展示文字，觀察兩者是否一致
- 體會「感覺哪裡不對」這種模糊直覺，可以交給 AI 從資料裡具體找出證據
- 理解 AI 找出矛盾之後，是交由老師判斷原因與後續行動，而不是替老師下定論
## 教學流程
### Step 1：設立情境
**Say:**
「林老師，學期末問卷收回來了，28 份。
你花了半小時瀏覽一遍。分數很好看：教學品質 4.3、師生溝通 4.2、整體滿意度 4.1——全部都在 4 分以上。
照理說應該沒事。
但你合上問卷的時候，心裡有一種微妙的不安：「好像哪裡不太對，但我說不出來。」
今天，我們來練習一件事：把這個「說不出來」的感覺，交給 AI 去找——看看它到底不對在哪裡。
準備好了嗎？說：**『開始』**」
**Check:** 等學生說「開始」
---
### Step 2：先展示量化分數
**Action:** Read `horizon-academy/parent-survey-scores.csv`，呈現量化評分表
**Present it like this:**
**量化評分**
| 評量項目 | 平均分 |
|---------|--------|
| 教學品質 | 4.3 |
| 師生溝通 | 4.2 |
| 作業設計 | 4.0 |
| 整體滿意度 | 4.1 |
**Say:**
「看分數，一切正常。全部 4 分以上，沒有明顯低分項目。
如果只看這一頁，你會說：家長滿意，沒問題。
但問卷還有另一半——開放式的文字填答。我把它拉出來給你看。
說：**『給我看』**」
**Check:** 等學生說「給我看」或類似的話
---
…Read the whole file at its exact version.
How to install
mdr add danyuchn/claude-code-for-tutors/start-3-2@git:20260910.cc5575cmdr add danyuchn/claude-code-for-tutors/start-3-2@sha256:cbe44da59c2f4b05Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_6gyh2hh26ohhb2sv)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260910.cc5575c latest | 2026-09-10 | cc5575c | 6,587 B | A | view · diff |
| git:20260902.392339e | 2026-09-02 | 392339e | 6,575 B | A | view · diff |
| git:20260829.d4c7f1b | 2026-08-29 | d4c7f1b | 6,124 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6587 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
danyuchn/claude-code-for-tutors · 23 stars · license NOASSERTION · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6gyh2hh26ohhb2sv GET https://markdownregistry.com/api/v1/resolve?ref=danyuchn/claude-code-for-tutors/start-3-2 GET https://markdownregistry.com/api/v1/blob/cbe44da59c2f4b0598688161baf69a687046513ea2fda451b5ccdd827baba494
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from danyuchn/claude-code-for-tutors
Every file in danyuchn/claude-code-for-tutors